Question

我正在尝试通过迭代元素来解析xml文件。

这是我打算做的基本方法。但是，无论何时调用此方法，我都会观察到泄漏。

代码：

std::string getUrl(std::vector<std::string> keyPath, std::string element, std::string fName)
{

    xmlDocPtr m_doc;
    xmlNodePtr m_cur;
    std::string m_fileName;
    bool isEmpty;
    int i=0;
    std::string value = "";
    isEmpty = false;
    m_fileName = fName;
    struct stat stat_buf;
    int rc = stat(m_fileName.c_str(), &stat_buf);
    if(rc==0)
    {
        m_doc = xmlParseFile(m_fileName.c_str());
    }
    else
    {
        isEmpty = true;
    }

    if(isEmpty)
    {
       value = "Empty file found";
       xmlFreeDoc(m_doc);
       xmlCleanupCharEncodingHandlers();
       xmlCleanupParser();
       return value;
    }
    if(m_doc != NULL)
    {
        m_cur = xmlDocGetRootElement(m_doc);
    }
    if(m_cur != NULL)
    {
        if(!xmlStrcmp(m_cur->name, (const xmlChar *)(keyPath.at(i).c_str())))
        {
            m_cur = m_cur->xmlChildrenNode;
            ++i;
        }
        else
        {
            value = "root element not found";
            return value;
        }
        while(m_cur != NULL)
        {
            if (!xmlStrcmp ( m_cur -> name, ( const xmlChar * ) keyPath.at(i).c_str()))
            {
                m_cur = m_cur->xmlChildrenNode;
                i++;
            }
            m_cur = m_cur -> next;
            if (!xmlStrcmp ( m_cur -> name, ( const xmlChar * ) keyPath.back().c_str()))
            {
                m_cur = m_cur->xmlChildrenNode;
                break;
            }
        }
        while (m_cur != NULL)
        {
        if (!xmlStrcmp ( m_cur -> name, ( const xmlChar * ) element.c_str()))
        {
            if(xmlNodeGetContent(m_cur->xmlChildrenNode) != NULL)
            value = (char*)(xmlNodeGetContent(m_cur->xmlChildrenNode));
            else
            value = "";
        }
        m_cur = m_cur -> next;
        }
    }

    //call the necessary cleanup APIs of libxml2 to free the dynamically allocated memory
    xmlFreeDoc(m_doc);
    xmlCleanupCharEncodingHandlers();
    xmlCleanupParser();

    if(!value.empty())
    {
        return value;
    }
    else
    {
        value = "value not found";
        return value;
    }
}

Valgrind泄漏如下：

==1598== 
==1598== HEAP SUMMARY:
==1598==     in use at exit: 139,402 bytes in 1,053 blocks
==1598==   total heap usage: 1,222 allocs, 169 frees, 284,997 bytes allocated
==1598== 
==1598== 28 bytes in 1 blocks are definitely lost in loss record 29 of 80
==1598==    at 0x4C2A6FE: malloc (vg_replace_malloc.c:296)
==1598==    by 0x526D928: xmlStrndup (in /usr/lib64/libxml2.so.2.9.1)
==1598==    by 0x40198D: getUrl(std::vector<std::string, std::allocator<std::string> >, std::string, std::string) (in /cluster/home/XmlParser)
==1598==    by 0x401BAE: parseXmlFile(std::vector<std::string, std::allocator<std::string> >, std::string, std::string) (in /cluster/home/XmlParser)
==1598==    by 0x402A56: main (in /cluster/home/XmlParser)
==1598== 
==1598== 28 bytes in 1 blocks are definitely lost in loss record 30 of 80
==1598==    at 0x4C2A6FE: malloc (vg_replace_malloc.c:296)
==1598==    by 0x526D928: xmlStrndup (in /usr/lib64/libxml2.so.2.9.1)
==1598==    by 0x4019A4: getUrl(std::vector<std::string, std::allocator<std::string> >, std::string, std::string) (in /cluster/home/XmlParser)
==1598==    by 0x401BAE: parseXmlFile(std::vector<std::string, std::allocator<std::string> >, std::string, std::string) (in /cluster/home/XmlParser)
==1598==    by 0x402A56: main (in /cluster/home/XmlParser)
==1598== 
==1598== 30 bytes in 1 blocks are definitely lost in loss record 31 of 80
==1598==    at 0x4C2A6FE: malloc (vg_replace_malloc.c:296)
==1598==    by 0x526D928: xmlStrndup (in /usr/lib64/libxml2.so.2.9.1)
==1598==    by 0x40198D: getUrl(std::vector<std::string, std::allocator<std::string> >, std::string, std::string) (in /cluster/home/XmlParser)
==1598==    by 0x401BAE: parseXmlFile(std::vector<std::string, std::allocator<std::string> >, std::string, std::string) (in /cluster/home/XmlParser)
==1598==    by 0x402CD2: main (in /cluster/home/XmlParser)
==1598== 
==1598== 30 bytes in 1 blocks are definitely lost in loss record 32 of 80
==1598==    at 0x4C2A6FE: malloc (vg_replace_malloc.c:296)
==1598==    by 0x526D928: xmlStrndup (in /usr/lib64/libxml2.so.2.9.1)
==1598==    by 0x4019A4: getUrl(std::vector<std::string, std::allocator<std::string> >, std::string, std::string) (in /cluster/home/XmlParser)
==1598==    by 0x401BAE: parseXmlFile(std::vector<std::string, std::allocator<std::string> >, std::string, std::string) (in /cluster/home/XmlParser)
==1598==    by 0x402CD2: main (in /cluster/home/XmlParser)
==1598== 
==1598== 30 bytes in 1 blocks are definitely lost in loss record 33 of 80
==1598==    at 0x4C2A6FE: malloc (vg_replace_malloc.c:296)
==1598==    by 0x526D928: xmlStrndup (in /usr/lib64/libxml2.so.2.9.1)
==1598==    by 0x40198D: getUrl(std::vector<std::string, std::allocator<std::string> >, std::string, std::string) (in /cluster/home/XmlParser)
==1598==    by 0x401FF4: parseXmlFile(std::vector<std::string, std::allocator<std::string> >, std::string, std::string) (in /cluster/home/XmlParser)
==1598==    by 0x402F30: main (in /cluster/home/XmlParser)
==1598== 
==1598== 30 bytes in 1 blocks are definitely lost in loss record 34 of 80
==1598==    at 0x4C2A6FE: malloc (vg_replace_malloc.c:296)
==1598==    by 0x526D928: xmlStrndup (in /usr/lib64/libxml2.so.2.9.1)
==1598==    by 0x4019A4: getUrl(std::vector<std::string, std::allocator<std::string> >, std::string, std::string) (in /cluster/home/XmlParser)
==1598==    by 0x401FF4: parseXmlFile(std::vector<std::string, std::allocator<std::string> >, std::string, std::string) (in /cluster/home/XmlParser)
==1598==    by 0x402F30: main (in /cluster/home/XmlParser)
==1598== 
==1598== 21,852 (176 direct, 21,676 indirect) bytes in 1 blocks are definitely lost in loss record 77 of 80
==1598==    at 0x4C2A6FE: malloc (vg_replace_malloc.c:296)
==1598==    by 0x5215324: xmlNewDoc (in /usr/lib64/libxml2.so.2.9.1)
==1598==    by 0x52C01B8: xmlSAX2StartDocument (in /usr/lib64/libxml2.so.2.9.1)
==1598==    by 0x520E25D: xmlParseDocument (in /usr/lib64/libxml2.so.2.9.1)
==1598==    by 0x520E561: xmlSAXParseFileWithData (in /usr/lib64/libxml2.so.2.9.1)
==1598==    by 0x40181A: getUrl(std::vector<std::string, std::allocator<std::string> >, std::string, std::string) (in /cluster/home/XmlParser)
==1598==    by 0x401BAE: parseXmlFile(std::vector<std::string, std::allocator<std::string> >, std::string, std::string) (in /cluster/home/XmlParser)
==1598==    by 0x402A56: main (in /cluster/home/XmlParser)
==1598== 
==1598== 21,852 (176 direct, 21,676 indirect) bytes in 1 blocks are definitely lost in loss record 78 of 80
==1598==    at 0x4C2A6FE: malloc (vg_replace_malloc.c:296)
==1598==    by 0x5215324: xmlNewDoc (in /usr/lib64/libxml2.so.2.9.1)
==1598==    by 0x52C01B8: xmlSAX2StartDocument (in /usr/lib64/libxml2.so.2.9.1)
==1598==    by 0x520E25D: xmlParseDocument (in /usr/lib64/libxml2.so.2.9.1)
==1598==    by 0x520E561: xmlSAXParseFileWithData (in /usr/lib64/libxml2.so.2.9.1)
==1598==    by 0x40181A: getUrl(std::vector<std::string, std::allocator<std::string> >, std::string, std::string) (in /cluster/home/XmlParser)
==1598==    by 0x401BAE: parseXmlFile(std::vector<std::string, std::allocator<std::string> >, std::string, std::string) (in /cluster/home/XmlParser)
==1598==    by 0x402CD2: main (in /cluster/home/XmlParser)
==1598== 
==1598== 21,852 (176 direct, 21,676 indirect) bytes in 1 blocks are definitely lost in loss record 79 of 80
==1598==    at 0x4C2A6FE: malloc (vg_replace_malloc.c:296)
==1598==    by 0x5215324: xmlNewDoc (in /usr/lib64/libxml2.so.2.9.1)
==1598==    by 0x52C01B8: xmlSAX2StartDocument (in /usr/lib64/libxml2.so.2.9.1)
==1598==    by 0x520E25D: xmlParseDocument (in /usr/lib64/libxml2.so.2.9.1)
==1598==    by 0x520E561: xmlSAXParseFileWithData (in /usr/lib64/libxml2.so.2.9.1)
==1598==    by 0x40181A: getUrl(std::vector<std::string, std::allocator<std::string> >, std::string, std::string) (in /cluster/home/XmlParser)
==1598==    by 0x401FF4: parseXmlFile(std::vector<std::string, std::allocator<std::string> >, std::string, std::string) (in /cluster/home/XmlParser)
==1598==    by 0x402F30: main (in /cluster/home/XmlParser)
==1598== 
==1598== LEAK SUMMARY:
==1598==    definitely lost: 704 bytes in 9 blocks
==1598==    indirectly lost: 65,028 bytes in 1,023 blocks
==1598==      possibly lost: 0 bytes in 0 blocks
==1598==    still reachable: 73,670 bytes in 21 blocks
==1598==         suppressed: 0 bytes in 0 blocks
==1598== Reachable blocks (those to which a pointer was found) are not shown.
==1598== To see them, rerun with: --leak-check=full --show-leak-kinds=all
==1598== 
==1598== For counts of detected and suppressed errors, rerun with: -v
==1598== ERROR SUMMARY: 9 errors from 9 contexts (suppressed: 0 from 0)

如果你能帮助我实际造成泄漏的事情，我真的很感激。提前致谢

Answer 1

这段代码导致两个内存泄漏：

if(xmlNodeGetContent(m_cur->xmlChildrenNode) != NULL)
    value = (char*)(xmlNodeGetContent(m_cur->xmlChildrenNode));
else
    value = "";

xmlNodeGetContent返回必须使用xmlFree释放的字符串。因此代码应如下所示：

xmlChar *content = xmlNodeGetContent(m_cur->xmlChildrenNode);
if (content != NULL) {
    value = (char*)content;
    xmlFree(content);
}
else {
    value = "";
}

您有时也会泄漏xmlDoc。这可能是由于未找到＆＃34;根元素造成的。返回路径，不会释放文档。

Answer 2

现在，nwellnhof已经为您提供了泄漏事件的答案。

我会尽力告诉你如何修复它们。注意未经测试的代码。

我们在这里（误）使用std::unique_ptr作为scope_guard。

首先制作一个genrel get string方法，修复无字符串问题。

std::string xmlGetString(xmlNodePtr m_cur) {
  std::unique_ptr<xmlChar> 
    content(xmlNodeGetContent(m_cur->xmlChildrenNode), xmlFree); // 1

  if (content != NULL) {
    return (char*)content;
  } else {
    return "";
  }
}

注1：xmlFree是std::unique_ptr

中的删除者

如果xmlFree没有为答案取NULL，则必须将其打包到另一个在调用xmlFree之前检查NULL的方法。

（这看起来非常低效，xmlNodeGetContent会复制一些内部数据，然后返回std::string，需要另一个文本副本，至少是字符串的最终副本到lvalue中可以省略来电者。）

与xmlFreeDoc相同的技巧，首先稍加重写

if (rc != 0) {
  // any other xml clean up needed???
  return "Empty file found";
}

然后宣布它为

std::unique_ptr<xmlDoc> m_doc(xmlParseFile(m_fileName.c_str()), Cleanup); 
// note the ptr is gone to the unique_ptr

和另一种方法

void Cleanup(xmlDocPtr m_doc) {
   xmlFreeDoc(m_doc);
   xmlCleanupCharEncodingHandlers();
   xmlCleanupParser();
}

然后当m_doc离开时，调用范围Cleanup。

现在你需要清理你的清理工作，这样你就不会做不必要的工作。

您应该将所有其他xml函数打包到某些c ++中或更改您的xml库。

在xmlStrndup中Valgrind内存泄漏

2 个答案: